All models

GPT-6.2 Astra

New Launched on IteraCompute

Online

OpenAI

openai/gpt-6.2-astra
Tool calling
SupportedTool calling · Supported
Reasoning
SupportedReasoning · Supported
Vision
SupportedVision · Supported
Streaming
SupportedStreaming · Supported
JSON mode
SupportedJSON mode · Supported

USD / 1M tokens

Input
$8.00
Cache read
$0.40
Cache write
—
Output
$40.00
Context
922K
Max output
128K
Precision
Official precision
Price checked

Overview

OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.

Version
gpt-6.2-astra
Input / output
text, image / text
Endpoint
/v1/chat/completions, /v1/responses, /v1/messages

API protocols and integration

Base URL · OpenAI SDK
https://api.iteracompute.com/v1
Authentication
Authorization: Bearer ITERACOMPUTE_API_KEY

Choose request fields, response parsing and stream completion by endpoint. This table describes wire formats; see this model's capabilities and verification scope.

Customer endpointModel statusInput / output budgetResultSSE completion
OpenAI Chat Completions
POST /v1/chat/completions
Declared for this modelmessages
max_tokens
choices[0].message.content[DONE]
OpenAI Responses
POST /v1/responses
Declared for this modelinput
max_output_tokens
output[] (SDK: output_text)response.completed
Anthropic Messages
POST /v1/messages
Declared for this modelmessages; system (top-level)
max_tokens (required)
content[]message_stop

For the Messages SDK use https://api.iteracompute.com as base URL; max_tokens is required. Do not reuse another protocol's fields.

View docs
LLMs.txt · Copy for an AI coding assistant

Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.

LLMs.txt
# IteraCompute · openai/gpt-6.2-astra

Model ID: openai/gpt-6.2-astra
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json

Use only the customer endpoints below. Request and response formats differ by protocol. An endpoint declaration does not certify every capability.

## Chat Completions
POST https://api.iteracompute.com/v1/chat/completions
Input: messages
Output budget: max_tokens
Read result: choices[0].message.content
SSE completion: [DONE]
Docs: https://iteracompute.com/docs.html#api-reference

## Responses
POST https://api.iteracompute.com/v1/responses
Input: input
Output budget: max_output_tokens
Read result: output[] (SDK: output_text)
SSE completion: response.completed
Docs: https://iteracompute.com/docs.html#responses-api

## Messages
POST https://api.iteracompute.com/v1/messages
Input: messages; system (top-level)
Output budget: max_tokens (required)
Read result: content[]
SSE completion: message_stop
Docs: https://iteracompute.com/docs.html#anthropic-messages

## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Parameter revision: ddcfe291c6d1a7ea3685beb95b3421dc9574cba9055c4d9fa1d30bfb9d0442a4
Context tokens: 922000
Maximum output tokens: 128000
Capability tools: configured enabled (see verification scope)
Capability vision: configured enabled (see verification scope)
Capability json_mode: configured enabled (see verification scope)
Capability reasoning: configured enabled (see verification scope)
Capability streaming: configured enabled (see verification scope)
- tools: array; accepted; min=unknown; max=unknown; default=Undisclosed. Tool definitions; the application executes tool calls and returns results.
- stream: boolean; accepted; min=unknown; max=unknown; default=Undisclosed. Enable SSE streaming; completion markers depend on the protocol.
- max_tokens: integer; accepted; min=16; max=128000; default=Undisclosed. Output token budget; includes reasoning where applicable. Chat Completions / Messages.
- response_format: object; accepted; min=unknown; max=unknown; default=Undisclosed. Text: Chat output format. Images: b64_json only; not text JSON mode.
- max_output_tokens: integer; accepted; min=16; max=128000; default=Undisclosed. Responses output budget. Chat acceptance must be checked separately.
- max_completion_tokens: integer; accepted; min=16; max=128000; default=Undisclosed. Alternative Chat output budget; use only when accepted by this model.

## Chat Completions example · JSON body
```json
{
  "model": "openai/gpt-6.2-astra",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256
}
```

## Responses example · JSON body
```json
{
  "model": "openai/gpt-6.2-astra",
  "input": "Reply OK",
  "max_output_tokens": 256
}
```

## Messages example · JSON body
```json
{
  "model": "openai/gpt-6.2-astra",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ]
}
```

## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.

Open plain text

API parameters

  • At an output budget of 16, all three protocols accepted the sampled request. A budget of 15 was rejected.
  • Function calls and tool replies were tested on Responses. A tested reasoning-enabled Chat route rejected tools.

These parameters and ranges describe the current route. Account and context limits also apply. Parameter acceptance does not establish model capability.

Tool calling
Supported
Reasoning
Supported
Vision
Supported
Streaming
Supported
JSON mode
Supported

Parameters and values

Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.

ParameterTypeAcceptanceRangeUsage / protocol
arrayAccepted—Tool definitions; the application executes tool calls and returns results.
booleanAccepted—Enable SSE streaming; completion markers depend on the protocol.
integerAccepted[16, 128000]Output token budget; includes reasoning where applicable. Chat Completions / Messages.
objectAccepted—Text: Chat output format. Images: b64_json only; not text JSON mode.
integerAccepted[16, 128000]Responses output budget. Chat acceptance must be checked separately.
integerAccepted[16, 128000]Alternative Chat output budget; use only when accepted by this model.

Current configuration example

POST /v1/chat/completions

Chat Completions request
{
  "model": "openai/gpt-6.2-astra",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256
}

Parameter revision:ddcfe291c6d1

API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="openai/gpt-6.2-astra",
    messages=[
      {
        "role": "user",
        "content": "Reply OK"
      }
    ],
    max_tokens=256,
)
print(response.choices[0].message.content)

Pricing

USD per million tokens. — means unknown. Account and subscription limits still apply.

Input$8.00
Cache read$0.40
Cache write—
Output$40.00
Version / Model ID
openai/gpt-6.2-astragpt-6.2-astra
Context
922K
Precision
Official precision
Price checked
Verification scope and sources
View verification scope and sources

2026-11-20 · Short requests verified text, usage and stream completion on Chat Completions, Responses and Messages. Red and blue image probes, short reasoning and JSON probes also returned observable results. Maximum token lengths are vendor specifications.

Complete token prices

USD per million tokens. Unknown prices are shown as —. Token ranges include cache reads and writes; ranges use (start, end].

Billing itemOur priceOfficial reference
Input$8$8
Cache read$0.4$0.4
Output$40$40
Cache write · 30 min$10$10
Cache write · 12 h$20$20

Our price · Input token range (0, 272000]

  • Input: $8
  • Cache read: $0.4
  • Output: $40
  • Cache write · 30 min: $10
  • Cache write · 12 h: $20

Our price · Input token range (272000, 922000]

  • Input: $16
  • Cache read: $0.8
  • Output: $60
  • Cache write · 30 min: $20
  • Cache write · 12 h: $40

Official reference · Input token range (0, 272000]

  • Input: $8
  • Cache read: $0.4
  • Output: $40
  • Cache write · 30 min: $10
  • Cache write · 12 h: $20

Official reference · Input token range (272000, 922000]

  • Input: $16
  • Cache read: $0.8
  • Output: $60
  • Cache write · 30 min: $20
  • Cache write · 12 h: $40
Revision: 5c417ae7069d

Vendor-documented context window · 1,050,000 tokens · Maximum output · 128,000 tokens ·

Cost calculator

USD · Estimate
Calculation mode
Advanced token usage

Input includes cache reads and writes; these portions must not overlap. Output already includes reasoning; enter reasoning as a subset, never add it twice. Count agent steps and retries as requests.

Estimated monthly cost

—USD

GPT-6.2 Astra

Cache hits and capacity are not guaranteed.

Cost breakdown
Uncached input
—
Cache read
—
Cache writes (5m + 1h)
—
Output (including reasoning)
—

Usage limits

  • OpenAI documents a 1,050,000-token context, up to 922,000 input tokens and 128,000 output tokens. Standard rates change above 272,000 input tokens.
  • At an output budget of 16, all three protocols accepted the sampled request. A budget of 15 was rejected.
  • Responses returned both cache-write TTL counters. In isolated tests the gateway cost and quote matched official rates.

Use cases

Coding

Text workflows

Agent tools

Integration tools and guides

FAQ

How do I call GPT-6.2 Astra?

Use Model ID openai/gpt-6.2-astra and the native fields in this page's API examples. Declared endpoints: /v1/chat/completions, /v1/responses, /v1/messages.

How is usage priced?

Use the current prices and billing units. Missing prices remain unknown, not free. The calculator uses native Gateway quotes; an estimate is not a bill.

Which parameters and limits apply?

Check the current parameter table and usage limits. Budget fields differ by protocol. Configured limits do not establish full-window quality or guarantee a maximum-length output.

New arrivals

Explore the models selected for New Arrivals, with API pricing, supported capabilities and integration guides.

View new arrivals
GoogleNew

Gemini 4 Hydrogen

gemini/gemini-4-hydrogen

Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.

Launched on IteraCompute

Input
$1.50
Output
$7.50

USD / 1M tokens

OpenAINew

GPT-6.2 Sol

openai/gpt-6.2-sol

OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.

Launched on IteraCompute

Input
$2.00
Output
$10.00

USD / 1M tokens

QwenNew

Qwen4-Max

qwen/qwen4-max

Qwen4-Max through Alibaba Cloud Model Studio, with text, reasoning, tools and image input.

Launched on IteraCompute

Input
$1.50
Output
$4.50

USD / 1M tokens